论文标题
模糊不变的内核自适应网络，用于单图像盲目脱毛
Blur Invariant Kernel-Adaptive Network for Single Image Blind deblurring
论文作者
论文摘要
我们提出了一种新颖的，盲目的，单图形脱毛的方法，该方法利用有关模糊内核的信息。我们的模型通过将其分为两个连续的任务来解决过度的问题：（1）模糊内核估计和（2）清晰的图像恢复。我们首先引入一个内核估计网络，该网络基于模糊图像的分析产生自适应模糊内核。该网络了解输入图像的模糊模式并训练以生成图像特异性模糊内核的估计。随后，我们提出了一个使用估计的模糊内核来恢复尖锐图像的脱毛网络。为了有效地使用内核，我们提出了一个内核自适应AE块，该块将模糊图像和模糊内核的特征编码为低维空间，然后同时解码它们以获得适当合成的特征表示。我们使用各种高斯模糊内核评估了Reds，GoPro和FlickR2K数据集的模型。实验表明，我们的模型可以在每个数据集上实现最先进的结果。
We present a novel, blind, single image deblurring method that utilizes information regarding blur kernels. Our model solves the deblurring problem by dividing it into two successive tasks: (1) blur kernel estimation and (2) sharp image restoration. We first introduce a kernel estimation network that produces adaptive blur kernels based on the analysis of the blurred image. The network learns the blur pattern of the input image and trains to generate the estimation of image-specific blur kernels. Subsequently, we propose a deblurring network that restores sharp images using the estimated blur kernel. To use the kernel efficiently, we propose a kernel-adaptive AE block that encodes features from both blurred images and blur kernels into a low dimensional space and then decodes them simultaneously to obtain an appropriately synthesized feature representation. We evaluate our model on REDS, GOPRO and Flickr2K datasets using various Gaussian blur kernels. Experiments show that our model can achieve state-of-the-art results on each dataset.
